PRR Project

Summary

1. TASKS TO BE ASSIGNED TO THE PROSPECTIVE EMPLOYEEThe prospective employee will be responsible for conducting advanced research studies concerning railway track monitoring, data acquisition and performance modelling for improved decisions concerning design and maintenance, including the following tasks:a) Smart Data Acquisition and Integration: Developing an intelligent data acquisition system, integrating data from diverse sources for comprehensive track monitoring.b) Big Data Analytics for Geometric Degradation: Utilising advanced data analytics techniques to detect long-term track geometry degradation patterns, enabling proactive maintenance.c) Railway Ballast Assessment and Predictive Maintenance: Employing big data analytics to assess ballast degradation and particle morphology, supported by machine learning algorithms.d) Data-Driven Numerical modelling Simulations: Leveraging data-driven numerical simulations using FEM and DEM to enhance track design and maintenance decisions.e) Intelligent Decision Support System: Developing an intelligent system integrating inspection records, simulations, and historical data for real-time track health monitoring.f) Dissemination and implementation of results.2. SCIENTIFIC PROFILE REQUIREDLNEC requires a researcher with experience in railway track design, monitoring, and performance evaluation, having also some experience in numerical modelling and data analytics. The researcher for this position must have a scientific profile with knowledge in transport infrastructures, structural health monitoring (SHM), and performance modelling.The researcher to be hired also needs to have clear interest and motivation to develop the identified tasks, and experience in joint research projects.3. RATIONALE TO HIRE FOR THE SCIENTIFIC AREAFollowing the major investments in the Portuguese railway network under the programme “Ferrovia 2020”, a significant expansion of this network is expected in years to come, according to the recently issued National Railway Plan.A high quality rail network is essential for sustainable mobility and represents a major asset that must be managed and preserved during its lifecycle, ensuring adequate conditions for the traffic while minimizing the costs associated.The proposed research will contribute to enhance the safety, efficiency, and longevity of railway networks, by harnessing the power of advanced analytics, predictive maintenance models, and real-time monitoring.4. RELEVANCE OF THE SCIENTIFIC PROFILE OF THE PROPOSED POSITION IN THE CONTEXT OF THE STATE-OF-THE-ARTThe current practice in railway track asset management and inspection underscores the need for advanced data-driven approaches. Traditional methods that rely on periodic inspections fall short in addressing the complexities involved in predicting the long-term track degradation and development of faults. Recent advances in data science, including machine learning algorithms, offer promising tools for analysing vast and diverse datasets generated by track monitoring systems, enabling the identification of nuanced patterns and trends.To benefit from these innovations, transport infrastructure management is advancing towards the development of intelligent decision support systems for SHM. While traditional methods have been primarily reactive, newer approaches are shifting towards proactive and predictive strategies. These systems are designed to continuously collect data from various sources, including inspection records, sensor networks, and simulation results, allowing for real-time monitoring and analysis of structural conditions.Recently there has been a growing emphasis on integrating data analytics, machine learning algorithms, and artificial intelligence into these decision support systems, enabling early detection of anomalies and potential issues and providing railway operators with valuable insights for informed decisions related to track maintenance and repairs. Such systems have the potential to enhance safety, reduce downtime, optimise maintenance costs for railway networks, and improve costumer experience.The full potential of intelligent decision support systems for SHM in railway infrastructures is yet to be realised. Challenges remain in integrating diverse data sources, ensuring data accuracy, and developing robust predictive models of the tracks behaviour, from a mechanistic point of view, and for the dynamic nature of railway operations. The research will address these challenges and push the boundaries of what is achievable in this field. By leveraging the latest advancements in data science, remote sensing, and numerical modelling, it seeks to create an intelligent decision support system for SHM of railway tracks, empowering railway operators with the tools needed to make proactive and data-driven decisions, ultimately enhancing the resilience and performance of railway infrastructures.